Predicting Future Queries from Log Data

1. A computing system configured to identify a predicted future query, the system comprising: one or more query logs configured to store queries issued by users in several partitions; and one or more prediction components configured to identify predicted future queries that a user is likely to issue in a certain time period based on a query history for the user and aggregated behaviors for a group of users corresponding to the queries stored in the query log for the group of users.

2. The computing system of claim 1 , further comprising one or more advertising platforms configured to use the predicted future queries to select proper advertisements as a function of time.

3. The computing system of claim 2 , wherein the selected advertisement is displayed after a predicted period of time associated with the predicted future queries expires.

4. The computing system of claim 2 , wherein the selected advertisement is displayed to the user after a predicted period of time has expired since the predicted future queries were identified.

5. The computing system of claim 4 , wherein the predicted period of time is one of a quarter year, a month, a bi-week, or a week.

6. The computing system of claim 1 , wherein the predicted future queries are associated with recurring events.

7. One or more computer readable storage media storing instructions for performing a method of generating a future query for a user, the method comprising: locating user queries and aggregate queries in a query log; generating a language model based on the query log; and selecting a future query based on the language model for the user.

8. The storage media of claim 7 , wherein the selected future query is based on previous activities of the user observed through previously received user queries and common behaviors of other users represented in query log.

9. The storage media of claim 7 , wherein the language model includes a background model and lifetime model.

10. The storage media of claim 7 , wherein the language model represents a statistical usage for queries received by the search engine.

11. The storage media of claim 7 , wherein the selected future query is associated with a predicted time period.

12. The storage media of claim 11 , wherein the predicted time period is one of: immediately, 24 hours, one month, three month, or one quarter.

13. The storage media of claim 7 , wherein the selected future query is configured for display to the user with an advertisement that relates the selected future query.

14. A computer-implemented method of selecting a future query, the method comprising: locating user queries and aggregate queries in a query log; generating a language model based on the query log; and selecting a future query based on the language model for the user.

15. The method of claim 14 , wherein the selected future query is based on previous activities of the user observed through previously received user queries and common behaviors of other users represented in query log.

16. The method of claim 14 , wherein the language model includes a background model and lifetime model.

17. The method of claim 14 , wherein the language model represents a statistical usage for queries received by the search engine.

18. The method of claim 14 , wherein the selected future query is associated with a probability identified in the language model.

19. The method of claim 18 , wherein the selected future query is associated with a predicted time period.

20. The method of claim 14 , wherein the selected future query is configured for display to the user with an advertisement that relates the selected future query.